salamandra-2b / perplexity_IQ4_NL.txt
robbiemu's picture
update for quantization
5dadba4
build: 3906 (7eee341b) with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.6.0
llama_model_loader: loaded meta data with 33 key-value pairs and 219 tensors from salamandra-2b_IQ4_NL.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.size_label str = 2.3B
llama_model_loader: - kv 3: general.license str = apache-2.0
llama_model_loader: - kv 4: general.tags arr[str,1] = ["text-generation"]
llama_model_loader: - kv 5: general.languages arr[str,36] = ["bg", "ca", "code", "cs", "cy", "da"...
llama_model_loader: - kv 6: llama.block_count u32 = 24
llama_model_loader: - kv 7: llama.context_length u32 = 8192
llama_model_loader: - kv 8: llama.embedding_length u32 = 2048
llama_model_loader: - kv 9: llama.feed_forward_length u32 = 5440
llama_model_loader: - kv 10: llama.attention.head_count u32 = 16
llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 16
llama_model_loader: - kv 12: llama.rope.freq_base f32 = 10000.000000
llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 14: general.file_type u32 = 25
llama_model_loader: - kv 15: llama.vocab_size u32 = 256000
llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 17: tokenizer.ggml.add_space_prefix bool = true
llama_model_loader: - kv 18: tokenizer.ggml.model str = llama
llama_model_loader: - kv 19: tokenizer.ggml.pre str = default
llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,256000] = ["<unk>", "<s>", "</s>", "<pad>", "<|...
llama_model_loader: - kv 21: tokenizer.ggml.scores arr[f32,256000] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 28: general.quantization_version u32 = 2
llama_model_loader: - kv 29: quantize.imatrix.file str = imatrix/oscar/imatrix.dat
llama_model_loader: - kv 30: quantize.imatrix.dataset str = ./imatrix/oscar/imatrix-dataset.txt
llama_model_loader: - kv 31: quantize.imatrix.entries_count i32 = 168
llama_model_loader: - kv 32: quantize.imatrix.chunks_count i32 = 44176
llama_model_loader: - type f32: 49 tensors
llama_model_loader: - type iq4_nl: 169 tensors
llama_model_loader: - type bf16: 1 tensors
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 104
llm_load_vocab: token to piece cache size = 1.8842 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 256000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 8192
llm_load_print_meta: n_embd = 2048
llm_load_print_meta: n_layer = 24
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 2048
llm_load_print_meta: n_embd_v_gqa = 2048
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 5440
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 8192
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: ssm_dt_b_c_rms = 0
llm_load_print_meta: model type = ?B
llm_load_print_meta: model ftype = IQ4_NL - 4.5 bpw
llm_load_print_meta: model params = 2.25 B
llm_load_print_meta: model size = 1.88 GiB (7.18 BPW)
llm_load_print_meta: general.name = n/a
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token = 145 '<0x0A>'
llm_load_print_meta: EOT token = 5 '<|im_end|>'
llm_load_print_meta: EOG token = 2 '</s>'
llm_load_print_meta: EOG token = 5 '<|im_end|>'
llm_load_print_meta: max token length = 72
llm_load_tensors: ggml ctx size = 0.20 MiB
llm_load_tensors: offloading 24 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 25/25 layers to GPU
llm_load_tensors: Metal buffer size = 1927.95 MiB
llm_load_tensors: CPU buffer size = 281.25 MiB
....................................
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_batch = 512
llama_new_context_with_model: n_ubatch = 128
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M3 Max
ggml_metal_init: picking default device: Apple M3 Max
ggml_metal_init: using embedded metal library
ggml_metal_init: GPU name: Apple M3 Max
ggml_metal_init: GPU family: MTLGPUFamilyApple9 (1009)
ggml_metal_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_init: GPU family: MTLGPUFamilyMetal3 (5001)
ggml_metal_init: simdgroup reduction support = true
ggml_metal_init: simdgroup matrix mul. support = true
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 42949.67 MB
llama_kv_cache_init: Metal KV buffer size = 1536.00 MiB
llama_new_context_with_model: KV self size = 1536.00 MiB, K (f16): 768.00 MiB, V (f16): 768.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.98 MiB
llama_new_context_with_model: Metal compute buffer size = 72.00 MiB
llama_new_context_with_model: CPU compute buffer size = 125.00 MiB
llama_new_context_with_model: graph nodes = 774
llama_new_context_with_model: graph splits = 3
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 15 (n_threads_batch = 15) / 16 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 1 | SVE = 0 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 1 | LLAMAFILE = 1 |
perplexity: tokenizing the input ..
perplexity: tokenization took 2736.46 ms
perplexity: calculating perplexity over 134 chunks, n_ctx=8192, batch_size=512, n_seq=1
perplexity: 10.91 seconds per pass - ETA 24.35 minutes
[1]16.0768,[2]16.1301,[3]14.7147,[4]14.5592,[5]13.9343,[6]13.5219,[7]14.2373,[8]13.7258,[9]13.4715,[10]12.8392,[11]13.4537,[12]13.5331,[13]14.4971,[14]14.7533,[15]14.7749,[16]15.2934,[17]15.5687,[18]15.5029,[19]15.5491,[20]15.8411,[21]15.8752,[22]14.0575,[23]14.2184,[24]13.8699,[25]13.4062,[26]13.0118,[27]12.8465,[28]12.6942,[29]12.6500,[30]12.4679,[31]12.6809,[32]12.7811,[33]13.2022,[34]13.4843,[35]13.7616,[36]13.5537,[37]13.5443,[38]13.6115,[39]13.4734,[40]13.4974,[41]13.4711,[42]13.3013,[43]13.2509,[44]13.4062,[45]13.5936,[46]13.4580,[47]13.6859,[48]13.7951,[49]14.0587,[50]14.2795,[51]14.3134,[52]14.5043,[53]14.7914,[54]15.0789,[55]15.1806,[56]15.0265,[57]14.9347,[58]14.6916,[59]14.5939,[60]14.4129,[61]14.4542,[62]14.5781,[63]14.7456,[64]14.7938,[65]14.8116,[66]14.9789,[67]14.9624,[68]14.8664,[69]14.7410,[70]14.6461,[71]14.6455,[72]14.5974,[73]14.6070,[74]14.5544,[75]14.5174,[76]14.4611,[77]14.5132,[78]14.5089,[79]14.5169,[80]14.5463,[81]14.3065,[82]14.2910,[83]14.1737,[84]14.2072,[85]14.2510,[86]14.4303,[87]14.4539,[88]14.5944,[89]14.6444,[90]14.7582,[91]14.8120,[92]14.6680,[93]14.7281,[94]14.7172,[95]14.8442,[96]15.0205,[97]15.0885,[98]15.1768,[99]15.2846,[100]15.3231,[101]15.3512,[102]15.3184,[103]15.2920,[104]15.2760,[105]15.2583,[106]15.1391,[107]15.0233,[108]15.0830,[109]15.1028,[110]15.0205,[111]14.9881,[112]14.8467,[113]14.7195,[114]14.7129,[115]14.6876,[116]14.6952,[117]14.5981,[118]14.4785,[119]14.4760,[120]14.5311,[121]14.5473,[122]14.5692,[123]14.6040,[124]14.6197,[125]14.6171,[126]14.6413,[127]14.6658,[128]14.7388,[129]14.7309,[130]14.7103,[131]14.7611,[132]14.7386,[133]14.6897,[134]14.5534,
Final estimate: PPL = 14.5534 +/- 0.05815
llama_perf_context_print: load time = 1300.25 ms
llama_perf_context_print: prompt eval time = 1397685.60 ms / 1097728 tokens ( 1.27 ms per token, 785.39 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 1448619.57 ms / 1097729 tokens
ggml_metal_free: deallocating